Qwen3-Embedding
Ranked 5 of 8 embedding models by recommenders
Open-weight multilingual embedding model with 32K context and several sizes, popular for local retrieval. Caveat: some find its latency too high for their use case.
Open-weight multilingual embedding model with 32K context and several sizes, popular for local retrieval. Caveat: some find its latency too high for their use case.
9 people gave an opinion
- recommend it
- 8
- criticize it
- 1
- approval share
- 89%
Recommended in 4 of 13 months
- November 2025: recommended
- December 2025: not recommended
- January 2026: not recommended
- February 2026: not recommended
- March 2026: recommended
- April 2026: recommended
- May 2026: recommended
- June 2026: not recommended
- July 2026: not recommended
- August 2026: not recommended
- September 2026: not recommended
- October 2026: not recommended
- November 2026: not recommended (month in progress)
Why it doesn’t carry the badge
- 8 people recommend itNeeds 10 or more, not met.
- 8 recommenders for every criticNeeds 2 to 1 or better, met.
- Recommended in 4 of 13 monthsNeeds 4 or more, met.
The same three rules apply to every product, and the badge can’t be bought. How the badge works
What people say about it
The reasons people give, with the number of comments that give each one. Open a reason to read what they said.
Why people recommend it
Each mark is one comment
Multilingual with consistent results across languages
“the embedding model (Qwen3) seems to normalize well across the languages I cover”
Comment from 4 Mar 2026 in “Cross-Lingual News Dedup at $100/Month – Embeddings, Pgvector, and UnionFind” “Open weights, multilingual, 32k context.”
Comment from 28 Nov 2025 in “28M Hacker News comments as vector embedding search dataset” 32K context fits a whole page
“Qwen because 32K is enough to basically fit a whole page into the context window”
Comment from 5 May 2026 in “Ask HN: Best Embedding Models?” “Open weights, multilingual, 32k context.”
Comment from 28 Nov 2025 in “28M Hacker News comments as vector embedding search dataset” Several model sizes for different hardware
“Specific models & sizes for specific use cases on specific hardware at specific speeds.”
Comment from 13 Mar 2026 in “Can I Run AI locally?” “Nice to see a smaller embedding model in the lineup.”
Comment from 20 Apr 2026 in “Qwen releases Qwen3-Embedding-0.6B”
What people warn about
Each mark is one comment
Latency too high for some uses
“the latency wasn't great for my usecase so I didn't pursue it much further”
Comment from 28 Nov 2025 in “So you wanna build a local RAG?”
Other embedding models people recommend
The four most recommended other embedding models, with the same counts for each, so you can compare like for like. The tick on each bar marks the 2 to 1 line the badge needs.
| Product | Recommend | Criticize | Approval | Months | Owned | Badge |
|---|---|---|---|---|---|---|
| EmbeddingGemma | 27 | 4 | 87% | 3 | — | — |
| Ternlight | 17 | 3 | 85% | 1 | — | — |
| CLIP by OpenAI | 10 | 5 | 67% | 6 | — | Approved |
| Gemini Embedding 2 | 9 | 3 | 75% | 3 | — | — |
| Qwen3-EmbeddingThis page | 8 | 1 | 89% | 4 | — | — |
What people said
All 9 comments that mention it, newest first. Each links to the original comment.
“Qwen because 32K is enough to basically fit a whole page into the context window”
“Nice to see a smaller embedding model in the lineup.”
“Specific models & sizes for specific use cases on specific hardware at specific speeds.”
“the embedding model (Qwen3) seems to normalize well across the languages I cover”
“It's junk compared to BGE M3 on my retrieval tasks”
“Also matryoshka and the ability to guide matches by using prefix instructions on the query.”
“the latency wasn't great for my usecase so I didn't pursue it much further”
“Open weights, multilingual, 32k context.”
“qwen3-embedding:4b is my current favorite for local RAG for good reason”
Counts come from 1,795,640 Hacker News comments, November 2025 to November 2026. How we count. Report a mistake.